© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11780
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and math symbols, and alphanumeric sequences that appear to be chemical or biological formulas.

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.68
    1
    -0.68
     ujednoznacz
    -0.66
    }`).
    -0.61
    RODUZIONE
    -0.59
    ]--;
    -0.57
     propOrder
    -0.57
     ①
    -0.57
     referenties
    -0.57
    ₁,
    -0.56
    POSITIVE LOGITS
    AutoresizingMask
    0.55
    UnknownFieldSet
    0.55
    4
    0.48
    Portail
    0.48
    InjectAttribute
    0.47
    AddTagHelper
    0.47
    .
    0.46
    DebuggerNonUser
    0.46
    databind
    0.45
     ArrayAdapter
    0.45
    Activations Density 6.786%

    No Known Activations